POLSCA: Polyhedral High-Level Synthesis with Compiler Transformations

被引：3

作者：

Zhao, Ruizhe ^{[1
]}

Cheng, Jianyi ^{[2
]}

Luk, Wayne ^{[1
]}

Constantinides, George A. ^{[2
]}

机构：

[1] Imperial Coll London, Dept Comp, London, England

[2] Imperial Coll London, Dept Elect & Elect Engn, London, England

来源：

2022 32ND INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE LOGIC AND APPLICATIONS, FPL | 2022年

基金：

英国工程与自然科学研究理事会;

关键词：

polyhedral model; high-level synthesis; compiler;

D O I：

10.1109/FPL57034.2022.00044

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Polyhedral optimization can parallelize nested affine loops for high-level synthesis (HLS), but polyhedral tools are HLS-agnostic and can worsen performance. Moreover, HLS tools require user directives which can produce unreadable polyhedral-transformed code. To address these two challenges, we present POLSCA, a compiler framework that improves polyhedral HLS workflow by automatic code transformation. POLSCA decomposes a design before polyhedral optimization to balance code complexity and parallelism, while revising memory interfaces of polyhedral-transformed code to make partitioning explicit for HLS tools; it enables designs to benefit more easily from polyhedral optimization. Experiments on Polybench/C show that POLSCA designs are 1.5 times faster on average compared with baseline designs generated directly from applying HLS on C code.

引用

页码：235 / 242

页数：8

共 50 条

[31] Optimizing Memory Hierarchy Allocation with Loop Transformations for High-Level Synthesis
Cong, Jason
Zhang, Peng
Zou, Yi
2012 49TH ACM/EDAC/IEEE DESIGN AUTOMATION CONFERENCE (DAC), 2012, : 1229 - 1234
[32] HIGH-LEVEL DSP SYNTHESIS USING CONCURRENT TRANSFORMATIONS, SCHEDULING, AND ALLOCATION
WANG, CY
PARHI, KK
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 1995, 14 (03) : 274 - 295
[33] Equivalence Checking of Scheduling with Speculative Code Transformations in High-Level Synthesis
Lee, Chi-Hui
Shih, Che-Hua
Huang, Juinn-Dar
Jou, Jing-Yang
2011 16TH ASIA AND SOUTH PACIFIC DESIGN AUTOMATION CONFERENCE (ASP-DAC), 2011,
[34] Polyhedral Bubble Insertion: A Method to Improve Nested Loop Pipelining for High-Level Synthesis
Morvan, Antoine
Derrien, Steven
Quinton, Patrice
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2013, 32 (03) : 339 - 352
[35] Valid transformations: A new class of loop transformations for high-level synthesis and pipelined scheduling applications
Rim, M
Jain, R
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 1996, 7 (04) : 399 - 410
[36] HIGH-LEVEL SYNTHESIS
PAWLAK, A
MICROPROCESSING AND MICROPROGRAMMING, 1992, 35 (1-5): : 261 - 261
[37] Developing a High-Level Language Compiler for a Computer with Programmable Architecture
Steinberg, Boris Ya.
Bugliy, Anton P.
Dubrov, Denis V.
Mikhailuts, Yury V.
Steinberg, Roman B.
CEE-SECR 2016: PROCEEDINGS OF THE 12TH CENTRAL & EASTERN EUROPEAN SOFTWARE ENGINEERING CONFERENCE IN RUSSIA, 2016,
[38] EAC: A compiler framework for high-level energy estimation and optimization
Kadayif, I
Kandemir, M
Vijaykrishnan, N
Irwin, MJ
Sivasubramaniam, A
DESIGN, AUTOMATION AND TEST IN EUROPE CONFERENCE AND EXHIBITION, 2002 PROCEEDINGS, 2002, : 436 - 442
[39] HIGH-LEVEL DEBUGGING ASSISTANCE VIA OPTIMIZING COMPILER TECHNOLOGY
OTTENSTEIN, KJ
SIGPLAN NOTICES, 1983, 18 (08): : 115 - 116
[40] Compiler-directed design space exploration for caching and prefetching data in high-level synthesis
Baradaran, N
Diniz, PC
FPT 05: 2005 IEEE INTERNATIONAL CONFERENCE ON FIELD PROGRAMMABLE TECHNOLOGY, PROCEEDINGS, 2005, : 233 - 240

← 1 2 3 4 5 →